
MMSkillRisk
Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…
adversarial-attackai-securitydata-exfiltration+7
6

Benchmark and evaluation harness testing whether LLM agents resist malicious instructions hidden in multimodal skill images, with 108 cases across…

Black-box security evaluation of five ISP cable modem/router gateways, analyzing firmware images and documenting 35+ vulnerabilities including…

Implementation of paper "DeeCLIP: A Robust and Generalizable Transformer-Based Framework for Detecting AI-Generated Images"


Universal local privilege escalation Proof-of-Concept exploit for CVE-2024-1086, working on most Linux kernels between v5.14 and v6.6, including…

Static analysis and structure recovery toolkit for ACE .qvm0-protected PE images